Get started
Author

Zorik Gekhman

Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
2024 · Zorik Gekhman, Gal Yona, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 85
PDF
TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models
2023 · Zorik Gekhman, Jonathan Herzig, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 33
PDF
KoBE: Knowledge-Based Machine Translation Evaluation
2020 · Zorik Gekhman, Roee Aharoni, et al. · 14
PDF
Confidence Improves Self-Consistency in LLMs
2025 · Amir Taubenfeld, Tom Sheffer, et al. · 12
PDF
RED-ACE: Robust Error Detection for ASR using Confidence Embeddings
2022 · Zorik Gekhman, Dina Zverinski, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 12
PDF
On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method
2023 · Zorik Gekhman, Nadav Oved, et al. · Transactions of the Association for Computational Linguistics · 9
PDF
Measuring the Robustness of NLP Models to Domain Shifts
2024 · Nitay Calderon, Naveh Porat, et al. · 5
PDF
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
2024 · Orgad, Hadas, Toker, Michael, et al. · arXiv (Cornell University) · 4
PDF
Can LLMs Learn Macroeconomic Narratives from Social Media?
2025 · Almog Gueta, Amir Feder, et al. · Findings of the Association for Computational Linguistics: NAACL · 3
PDF
Inside-Out: Hidden Factual Knowledge in LLMs
2025 · Gekhman, Zorik, David, Eyal Ben, et al. · arXiv (Cornell University) · 1
PDF
NL-Eye: Abductive NLI for Images
2024 · Ventura, Mor, Toker, Michael, et al. · arXiv (Cornell University) · 1
PDF
Using Text Injection to Improve Recognition of Personal Identifiers in Speech
2023 · Yochai Blau, Rohan Agrawal, et al. · Interspeech (USB) · 1
PDF
Measuring the Robustness of NLP Models to Domain Shifts
2023 · Calderon, Nitay, Porat, Naveh, et al. · arXiv (Cornell University) · 1
PDF
X (Twitter) IDs and LLM-Generated Analyses for Economic Narratives: Datasets for Pre-pandemic (2007-2020) and Post-LLM training cutoff (2021-2023)
2026 · Almog Gueta, Amir Feder, et al. · ICPSR Data Holdings
Verifiable Social Reasoning for LLM Assistants
2026 · Taubenfeld, Amir, Gekhman, Zorik, et al. · arXiv (Cornell University)
PDF
Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs
2026 · Association for Computational Linguistics 2026, Ein-Dor, Liat, et al. · Underline Science Inc.
Why Fine-Tuning Encourages Hallucinations and How to Fix It
2026 · Kaplan, Guy, Gekhman, Zorik, et al. · arXiv (Cornell University)
PDF
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
2026 · Gekhman, Zorik, Aharoni, Roee, et al. · arXiv (Cornell University)
PDF
Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
2026 · Calderon, Nitay, Ben-David, Eyal, et al. · arXiv (Cornell University)
PDF
Evaluating Alignment of Behavioral Dispositions in LLMs
2026 · Taubenfeld, Amir, Gekhman, Zorik, et al. · arXiv (Cornell University)
PDF
Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs
2026 · Yehonatan Peisakhovsky, Zorik Gekhman, et al.
PDF
Works count: 32
Citation count: 181
H-index: 6
I10-index: 5
Year
Topic
Type